Skip to content
ADE Index

cmux vs Goose vs HumanLayer

Up to four tools, row by row. We do not guess: a cell we have not checked says so.

How they differ

Price
Pick this if…

Paraphrased from each maker’s own description. Select a line for the quote.

Capabilities not yet checked for all
  • · also Goose
  • · also cmux

Checked for Goose, not yet for cmux and HumanLayer: Model providers (, , , , , SpaceXSI (Grok), , , , , , , , Meta AI (Llama), , Microsoft Foundry (Azure AI Foundry), , , , , OVHcloud AI Endpoints, , FriendliAI, , , , , , , , , , Amazon SageMaker AI, , , , , , , )

Checked for cmux and HumanLayer, not yet for Goose: Agents it runs (cmux: , , , , , ; HumanLayer: , )

Checked for cmux and Goose, not yet for HumanLayer: Editors and systems (cmux: , , ; Goose: , , , )

Same for all 3 (2): Bring your own key: Yes · Agent teams
  • Bring your own key: Yes · ·
  • Agent teams · ·

Provider names use the same listing as each tool page. Dotted values open their quote. A capability not shown is not yet checked; the tool may still have it.

About these tools

cmux

Goose

HumanLayer

How to read the Index score

At a glance

Index score out of 100

cmux42Goose33HumanLayer15

Mindshare HN mentions, 90 days

cmux46Goose20HumanLayer3

Adoption GitHub stars, not scored

cmux28.8kGoose56.7kHumanLayer12.9k

Release days last 90 days

cmux7Goose17HumanLayer0

Lowest monthly plan billed monthly, lower is cheaper

cmux$50 /moGooseNot yet checkedHumanLayer$100 /user/mo

Platforms listed surfaces

cmux3Goose6HumanLayer1

Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only. After activation, the score is 80% mindshare plus 20% of the greater of mindshare and the vote score. GitHub stars do not affect the Index score. Mindshare uses a log scale; votes use the square-root curve and a 100-vote floor. Ranks use unrounded scores. Mindshare and adoption bars are log-scaled; the others are linear within this comparison. How the score is built

Differences only
3 of 4
cmuxmanaflow-ai · Desktop app
Goosegoose · Desktop app
HumanLayerHumanLayer · Desktop app
Interface
Workspace sidebar of agent tasks, Claude Code and Codex panes, a dev server and browser splits
New terminal UI: goose searching, reading and editing Rust files while thinking
What it is
Native macOS terminal with agent notifications, split panes and a CLI
Desktop and CLI agent for code, workflows and automation
Run coding agents on your machines, with shared tasks, plans and reviews
Category
Agent workspace
Agent workspace
Agent workspace
What it does
Form
Desktop appiOS app
Desktop app
Desktop appWeb
Parallel agents
Yes
Yes
Not established
Worktree isolation
Not established
Not established
Yes
Task board
Not established
Not established
Yes
Agent teams
Yes
Yes
Yes
Review & diffs
Not established
Not established
Yes
Remote session control
Yes · beta · paid tier only
Not established
Not established
Team collaboration
Not established
Not established
Yes
Agent & model switching
Not established
Not established
Yes
Pricing
Starts at (billing shown)
Lowest monthly plan
Not yet checked
Free tier
Yes
Plans
Bring your own key
Yes
Yes
Yes
Runs on
JetBrains
Not yet checked
Yes
Not yet checked
Linux
Not yet checked
Yes
Not yet checked
Terminal
Yes
Yes
Not yet checked
VS Code
Not yet checked
Yes
Not yet checked
Web
Not yet checked
Not yet checked
Yes
Windows
Not yet checked
Yes
Not yet checked
iOS app
Yes
Not yet checked
Not yet checked
macOS
Yes
Yes
Not yet checked
Models and agents
Model providers
Not yet checked
AnthropicOpenAIGoogleOpenRouterOllamaSpaceXSI (Grok)Amazon BedrockLM Studio
+32 more model providers
GroqMistralGitHub CopilotAzure OpenAICerebrasMeta AI (Llama)LiteLLMMicrosoft Foundry (Azure AI Foundry)Novita AIPerplexityScalewayVeniceOVHcloud AI EndpointsAtomic ChatFriendliAIDatabricksTrustedRouterEmpirioLabs AINEAR AI CloudAI/ML APIAvianLemonadeDocker Model RunnerTetrate Agent Router ServiceAmazon SageMaker AIGondolallmmanOnysoft AI GatewayRamaLamaRoutstrSayGMSnowflake
Not every provider checked yet
Not yet checkedSource
Models
Not yet checked
AnthropicOpenAIGoogleOllamaOpenRouterAzureBedrockClaudeGemini
Not yet checked
Drives these agents
Claude CodeCodexOpenCodeGemini CLIKiroAider
Not yet checked
Claude CodeCodex
Source and activity
Source
GitHub stars
Most
Release days, last 90 days
7
17Most
0
Release days per week
Latest release, any channel
v0.65.2.2 27 Oct 2026
v1.60.1 18 Nov 2026
Index score
Score and rank
42 #23 Score 41.8; ranked on the unrounded score
33 #33 Score 33.1; ranked on the unrounded score
15 #91 Score 15.1; ranked on the unrounded score
Mindshare
4246 Hacker News mentions in the last 90 days
3320 Hacker News mentions in the last 90 days
153 Hacker News mentions in the last 90 days
Adoption, not scored
8428,813 stars, read 18 Nov 2026
9056,732 stars, read 18 Nov 2026
7812,906 stars, read 18 Nov 2026
Votes
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
—Votes can only raise a score: up to 20% of it reflects upvotes, graded on a curve against the most-voted tool. The square-root curve has a floor of 100 effective votes. Votes decay with a 90-day half-life. Maker self-votes do not count. Counts below 10 are hidden for display only.
Rank history
First ranked 18 Nov 2026
First ranked 18 Nov 2026
First ranked 18 Nov 2026
Full page

Watch cmux vs Goose vs HumanLayer on YouTube

More comparisons

Build your own